虽然已经出现了 MobileNetv1/v2/v3
和 ShuffleNetv1/v2
这种为移动端(CPU)设计的轻量级网络,但是它们所采用的基础技术-深度可分离卷积技术并不适用于 NPU
芯片(基于专用集成电路 (ASIC) 的边缘计算系统)。
Although some approaches were designed exclusively for mobile CPU [10, 30, 9, 32, 41, 23], the depth-wise convolution they adopted is usually not compatible with industrial IC design such as Application-Specific Integrated Circuit (ASIC) for edge-computing systems.
虽然有些方法是专门为移动端(CPU)设计的,但它们采用的深度卷积通常与工业IC设计不兼容,例如用于边缘计算系统的专用集成电路(ASIC)。
相当于作者是提出了问题
接着开始讲怎么解决问题?
在本研究中,我们探讨了如 ResNet、ResNeXt 和 DenseNet 等最先进方法的计算负担。我们进一步开发了计算效率高的组件,使上述网络能够同时部署在cpu和移动gpu上,而不会牺牲性能。
Andrew G Howard, Menglong Zhu, Bo Chen, Dmitry Kalenichenko, Weijun Wang, Tobias Weyand, Marco Andreetto, and Hartwig Adam. MobileNets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861, 2017.
Mark Sandler, Andrew Howard, Menglong Zhu, Andrey Zhmoginov, and Liang-Chieh Chen. MobileNetV2: Inverted residuals and linear bottlenecks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition(CVPR), pages 4510–4520, 2018.
Andrew Howard, Mark Sandler, Grace Chu, Liang-Chieh Chen, Bo Chen, Mingxing Tan, Weijun Wang, Yukun Zhu, Ruoming Pang, Vijay Vasudevan, et al. Searching for MobileNetV3. In Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2019.
Mingxing Tan, Bo Chen, Ruoming Pang, Vijay Vasudevan,Mark Sandler, Andrew Howard, and Quoc V Le. MNASnet: Platform-aware neural architecture search for mobile. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 2820–2828, 2019.
Xiangyu Zhang, Xinyu Zhou, Mengxiao Lin, and Jian Sun.ShuffleNet: An extremely efficient convolutional neural network for mobile devices. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR),pages 6848–6856, 2018.
Ningning Ma, Xiangyu Zhang, Hai-Tao Zheng, and Jian Sun.ShuffleNetV2: Practical guidelines for efficient cnn architecture design. In Proceedings of the European Conference on Computer Vision (ECCV), pages 116–131, 2018.